arXiv:2609.36672v1 Announce Type: new Abstract: Efficient exploration in high-dimensional decision spaces remains a central challenge for decision-making systems. Humans, in contrast, can navigate la...
arXiv:2607. 14192v1 Announce Type: new Abstract: As recommender systems mature in the past few years, their optimization objectives have evolved from a primary focusing on short-term behavioral signals to a broader emphasis on long-term user engagement and retention.
arXiv:2609.36473v1 Announce Type: new Abstract: Temporal abstraction via options can improve exploration in large environments. However, existing option discovery algorithms find subgoals that target...
SteerGR is a framework that enables concept-level control in generative recommendation for game discovery. It uses sparse autoencoders to define play concepts with an LLM, discover and select features associated with those concepts, and then intervene on the selected features to steer recommendations without retraining the model. Experiments on two industrial generative recommendation models demonstrate that the selected features can successfully steer recommendations toward or away from target concepts.
arXiv:2511. 22130v2 Announce Type: replace Abstract: To navigate ever-shifting real-world environments, agents must grapple with incomplete knowledge and adapt their strategies through experience.
arXiv:2606. 19476v1 Announce Type: cross Abstract: Effective machine learning depends not only on how we model data, but also on what data we choose to collect.
arXiv:2609.15094v1 Announce Type: cross Abstract: In industrial recommendation feeds, presenting a static headline for an item often fails to satisfy the diverse, multimodal interests of the user pop...
arXiv:2602. 17976v2 Announce Type: replace-cross Abstract: In active sequential testing, also termed pure exploration, a learner is tasked with the goal to adaptively acquire information so as to identify an unknown ground-truth hypothesis with as few queries as possible.
arXiv:2504. 17356v3 Announce Type: replace Abstract: Feature selection aims to preprocess the target dataset, find an optimal and most streamlined feature subset, and enhance the downstream machine learning task.
arXiv:2609.07575v1 Announce Type: cross Abstract: This work introduces an alternative view of efficient exploration and studies its theoretical and empirical implications in the absence of extrinsic...
The paper introduces a retrieval‑grounded credit‑assignment method for generative recommenders that use Semantic IDs (SIDs). By structuring each autoregressive trace into a history summary, a set of interest hypotheses, and a final SID, a frozen retriever verifies each hypothesis as a catalog query. Rewards are assigned at the hypothesis level when any query retrieves the target within the top‑K, allowing distinct updates for rollouts that share the same SID reward and improving SID recommendation performance on Amazon Reviews datasets.
The paper proposes a method to improve reward learning by shifting the burden of clarifying underspecified features from humans to robots. It introduces an informed prior that directs preference queries toward the most uncertain features and pairs each query with an explanation that guides human attention. Experiments show that this approach outperforms standard active preference learning, especially when human effort is limited, and that the prior and explanations synergistically enhance reward recovery.